Automatic tracking shooting method and device for motion in fixed score area, and storage medium

Abstract

The embodiment of the invention provides an automatic tracking shooting method and device for motion in a fixed score area and a storage medium, and the method comprises the steps: recognizing the position of a tracking target in a real-time shooting image and the position of the fixed score area, and when the position of the tracking target exceeds a first preset range, carrying out the automatic tracking shooting of the motion in the fixed score area; adjusting the shooting angle of the holder so as to track and shoot the tracking target; and when the position of the fixed score area is located in a second preset range and the position of the tracking target is located in a third preset range, locking the shooting angle of the pan-tilt. According to the method, the fixed score area and the to-be-tracked target in the real-time video image are identified and the position of the fixed score area and the to-be-tracked target is judged through the target identification algorithm, and the tracking or locking state of the holder is dynamically adjusted, so that intense activities around the fixed score area can be stably shot in automatic tracking shooting, and image jitter is reduced.

Description

Technical Field

[0001] Embodiments of the present application relate to the fields of computer vision technology and motion tracking shooting, and particularly to an automatic tracking shooting method, device, and computing device for the motion of a fixed scoring area. Background Art

[0002] In the field of computer vision technology, it is a relatively common solution to use a rotatable pan-tilt to automatically track a target. Among them, the recognition of the target usually adopts a face recognition solution, and when automatically tracking, the rotation of the pan-tilt is strictly controlled according to the position of the target. For example, CN119653240A tracks the target and determines whether to rotate the pan-tilt in the above manner. However, when applying the general computer vision technology solution to the field of motion tracking shooting, especially when tracking and shooting the motion with a fixed scoring area, there will be some difficult-to-solve problems.

[0003] First, different from the sports in fixed court areas such as volleyball, table tennis, and badminton, which usually score based on the mistakes of one side against the ball, the sports with a fixed scoring area such as basketball, football, hockey, and rugby will have a fixed scoring area, that is, the basket or goal, and score based on the behavior of one side against the ball entering the scoring area. Therefore, around the fixed scoring area, there will be rapid and frequent back-and-forth running of athletes, and such a scene is exactly the exciting moment of a game. In this scenario, if the existing tracking solution is mechanically implemented, the pan-tilt will repeatedly fine-tune and rotate within a small range, resulting in frequent jitter of the captured image.

[0004] Secondly, compared with the general target tracking scenario, the motion tracking shooting scenario has more complexity and unpredictability. Whether using a person or a ball as the tracking target, the situation of tracking loss may occur, and the general target tracking solution does not give a solution to this scenario.

[0005] It should be known that in the general automatic tracking target shooting scenario, the foregoing two problems will not occur. Therefore, those skilled in the art do not find the foregoing technical problems and the need for a technical solution. The present application is based on the above-mentioned defects existing when applying the general automatic tracking target shooting solution in the automatic tracking shooting scenario of the motion with a fixed scoring area. Summary of the Invention

[0006] In view of this, the present application provides an automatic tracking shooting solution for the motion of a fixed scoring area, aiming to improve the stability of the automatic tracking shooting of the motion of a fixed scoring area.

[0007] In the first aspect of the present application, an automatic tracking shooting method for the motion of a fixed scoring area is provided, which is characterized by including:

[0008] S1: Identify the position of the tracking target and the position of the fixed scoring area in the real-time captured image;

[0009] S3: When the position of the fixed scoring area is within the second preset range and the position of the tracking target is within the third preset range, suspend the execution of S2, lock the shooting angle of the pan-tilt head. The first preset range is included in the third preset range.

[0010] S3: When the position of the fixed scoring area is within the second preset range and the position of the tracking target is within the third preset range, suspend the execution of S2, lock the shooting angle of the pan-tilt head. The first preset range is included in the third preset range.

[0011] Preferably, the tracking target is at least one of a player, a crowd, or a ball.

[0012] According to an embodiment of the present application, the automatic tracking shooting method for the movement of the fixed scoring area further includes:

[0013] S4: When the position of the tracking target exceeds the third preset range, cancel the locking of the shooting angle of the pan-tilt head and execute S2.

[0014] When the position of the tracking target exceeds the first preset range, adjusting the shooting angle of the pan-tilt head includes:

[0015] When the position of the tracking target is outside the left side of the first preset range, move the shooting angle of the pan-tilt head to the left until the position of the tracking target is within the first preset range again;

[0016] When the position of the tracking target is outside the right side of the first preset range, move the shooting angle of the pan-tilt head to the right until the position of the tracking target is within the first preset range again.

[0017] According to an embodiment of the present application, when the tracking target is a player, identifying the position of the tracking target in the real-time captured image includes:

[0018] Pre-acquire the jersey features of the tracking target, where the jersey features include the target jersey number and the target jersey color;

[0019] Obtain all human targets in the real-time captured image, crop the jersey number area of each human target and send it into the number classification model, obtain the jersey number of each human target, and match it with the target jersey number;

[0020] If the match is successful, obtain the jersey color of the human target with the successful match, and match it with the target jersey color; if the match is successful, determine that the human target with the successful match is the tracking target.

[0021] According to an embodiment of the present application, when the tracking target is a crowd, use the average value of the position coordinates of all targets in the crowd as the position of the tracking target.

[0022] According to an embodiment of the present application, when the tracking target is a ball, identifying the position of the tracking target in the real-time captured image includes;

[0023] When the tracking target cannot be identified in the real-time captured image, trace back to the first position of the tracking target when it was last identified in the last preset number of frames before the real-time captured image, and use the first position as the position of the tracking target.

[0024] In a second aspect of the present application, there is provided another automatic tracking shooting method for fixed scoring area movement, which is characterized by including:

[0025] S1: Identify the position of the tracking target and the position of the fixed scoring area in the real-time captured image;

[0026] S2: When the position of the tracking target exceeds the first preset range, adjust the shooting angle of the pan-tilt head to track and shoot the tracking target;

[0027] S31: When the position of the fixed scoring area is within the second preset range and the number of human targets within the second preset range is not less than the preset value, suspend the execution of S2 and lock the shooting angle of the pan-tilt head;

[0028] S41: When the number of human targets within the second preset range is less than the preset value, cancel the locking of the pan-tilt head angle and execute step S2.

[0029] Preferably, the tracking target is at least one of a player, a crowd, or a ball.

[0030] When the position of the tracking target exceeds the first preset range in the center of the real-time captured image, adjusting the shooting angle of the pan-tilt head includes:

[0031] When the position of the tracking target is outside the left side of the first preset range, move the shooting angle of the pan-tilt head to the left until the position of the tracking target is back within the first preset range;

[0032] When the position of the tracking target is outside the right side of the first preset range, move the shooting angle of the pan-tilt head to the right until the position of the tracking target is back within the first preset range.

[0033] According to an embodiment of the present application, when the tracking target is a player, identifying the position of the tracking target in the real-time captured image includes;

[0034] Pre-acquire the jersey characteristics of the tracking target, where the jersey characteristics include the target jersey number and the target jersey color;

[0035] Acquire all human targets in the real-time captured image, crop the jersey number area of each human target and send it into the number classification model to obtain the jersey number of each human target, and match it with the target jersey number;

[0036] If the matching is successful, obtain the jersey color of the human target for which the matching is successful, and match it with the target jersey color; if the matching is successful, determine the human target for which the matching is successful as the tracking target.

[0037] According to an embodiment of the present application, when the tracking target is a crowd, the position of the tracking target is the average value of all target position coordinates in the crowd.

[0038] According to an embodiment of the present application, when the tracking target is a ball, identify the position of the tracking target in the real-time captured image, including;

[0039] When the tracking target cannot be identified in the real-time captured image, trace back to the first position of the tracking target when it was last identified in a preset number of frames before the real-time captured image, and use the first position as the position of the tracking target.

[0040] In a third aspect of the present application, an automatic tracking shooting device is provided, including a shooting module, an analysis module and a rotation module. The shooting module is physically connected to the rotation module. The rotation module is adapted to rotate horizontally. The shooting module is adapted to continuously obtain a real-time captured image and send the real-time captured image to the analysis module; the analysis module is adapted to execute the method of the first aspect or the second aspect of the present application and send a rotation instruction to the rotation module: the rotation module is adapted to change the angle of the shooting module according to the rotation instruction.

[0041] In a fourth aspect of the present application, an electronic device is provided, including a memory and a processor. A computer program is stored on the memory. When the processor executes the computer program, the method of the first aspect or the second aspect of the present application is implemented.

[0042] In a fifth aspect of the present application, a computer-readable storage medium is provided, on which a computer program is stored. When the computer program is executed by a processor, the method of the first aspect or the second aspect of the present application is implemented.

[0043] The automatic tracking shooting method for fixed scoring area movement provided by the embodiments of the present application uses a target recognition algorithm to identify and judge the position of the fixed scoring area and the target to be tracked in the real-time video image, and dynamically adjusts the tracking or locking state of the pan-tilt head, so that stable shooting can be achieved for the intense activities around the fixed scoring area during automatic tracking shooting, reducing image jitter. BRIEF DESCRIPTION OF THE DRAWINGS

[0044] Combined with the drawings and referring to the following detailed description, the above and other features, advantages and aspects of the embodiments of the present application will become more obvious. In the drawings, the same or similar reference numerals represent the same or similar elements, where:

[0045] Figure 1Flowchart of an automatic tracking shooting method for a fixed scoring area movement according to an embodiment of the present application;

[0046] Figure 2 Flowchart of a method for identifying the position of a player in a real-time shooting scene according to an embodiment of the present application;

[0047] Figure 3 Flowchart of another automatic tracking shooting method for a fixed scoring area movement according to an embodiment of the present application;

[0048] Figure 4 Example diagram of the division of a visible area and a preset range according to an embodiment of the present application;

[0049] Figure 5 Flowchart of yet another automatic tracking shooting method for a fixed scoring area movement according to an embodiment of the present application;

[0050] Figure 6 Block diagram of an automatic tracking shooting device according to an embodiment of the present application;

[0051] Figure 7 Structural schematic diagram of a terminal device or a server suitable for implementing the embodiments of the present application. Detailed implementation manners

[0052] To make the objectives, technical solutions, and advantages of the embodiments of the present application clearer, the technical solutions in the embodiments of the present application will be clearly and completely described below with reference to the accompanying drawings in the embodiments of the present application. Obviously, the described embodiments are some, but not all, of the embodiments of the present application. All other embodiments obtained by those of ordinary skill in the art based on the embodiments of the present application without creative efforts shall fall within the protection scope of the present application.

[0053] In the field of computer vision analysis, it is usually default that the origin of the coordinate system is located at the upper left corner of the screen. In each embodiment of the present application, unless otherwise stated, the upper left corner is used as the origin of the screen coordinate system; those skilled in the art should be aware that such a coordinate system setting is not absolutely fixed. When the origin of the coordinate system is set at any position inside or outside the screen, the corresponding technical solutions obtained by making simple adjustments to this solution without creative efforts shall fall within the protection scope of the present application.

[0054] In addition, the term "and / or" in this article is only a description of the association relationship between associated objects, indicating that there can be three relationships. For example, A and / or B can represent: A exists alone, A and B exist simultaneously, and B exists alone. In addition, the character " / " in this article generally represents an "or" relationship between the preceding and following associated objects.

[0055] Figure 1 The flowchart of an automatic tracking shooting method for a fixed scoring area movement according to an embodiment of the present application. Refer to Figure 1 , the method includes:

[0056] S1: Identify the positions of the tracking target and the fixed scoring area in the real-time shooting screen.

[0057] The technical solution of the present application is directed to an automatic tracking shooting scenario for a fixed scoring area movement. The movement of the fixed scoring area means that there is a fixed scoring area in the sports field, and the sports activity with the entry of a specific target into the fixed scoring area as the goal, such as basketball with the ball entering the basket as the scoring event, football, hockey, ice hockey, water polo, rugby, handball, etc. with the ball entering the goal as the scoring. The position of the fixed scoring area is the position where the basket or goal is located.

[0058] In a possible implementation, the identification of the tracking target and the position of the fixed scoring area is performed using a target recognition algorithm. The specific selection of the target recognition algorithm in the present application is not limited: the YOLOv8 model can be used, or other recognition algorithms such as CNN (Convolutional Neural Network) and ViT (Vision Transformer) can also be used. To achieve more accurate recognition results, a large number of labeled pictures can be used to train the algorithm model. The training of the algorithm and the model is a common technical means that those skilled in the art should know and does not belong to the content protected by the present application, so it will not be elaborated here. The target recognition algorithm represents each recognized target with four parameters: the horizontal and vertical coordinates of the center point of the target box and the width and height of the target box. In a possible implementation, the positions of the tracking target and the fixed scoring area are represented by the center points of the corresponding target recognition boxes.

[0059] The present application provides three target tracking solutions for the automatic tracking shooting of sports, tracking a single player, tracking a crowd, or tracking a ball. These three solutions can be used alternatively, or can be selected according to conditions in the overall tracking solution. The present application does not limit this. The following separately introduces the specific implementation methods of these three target trackings.

[0060] I. The tracking target is a player:

[0061] In the scenario of tracking a single player, preferably, the player to be tracked is determined by matching the jersey features. Figure 2 The flowchart of a method for identifying the position of a player in a real-time shooting screen according to an embodiment of the present application, as Figure 2 shown:

[0062] S201: Pre-acquire the jersey features of the target to be tracked, where the features include the target jersey number and the target jersey color. That is, pre-enter the jersey number and jersey color of the target to be tracked for use as a matching benchmark in subsequent tracking and shooting. The pre-entry of the jersey number and jersey color of the target to be tracked can be obtained through model recognition by uploading a complete jersey photo.

[0063] S202: Obtain all human targets in the real-time captured image, crop the jersey number area of each human target and send it to the number classification model to obtain the jersey number of each human target and match it with the target jersey number.

[0064] Specifically, use the target detection model to detect human targets in the real-time captured image, extract all human targets, and crop the area of the jersey number; use the classification model to identify the jersey number of the human target and match the number with the preset target jersey number. If the numbers are the same, it is considered a successful match. There are no restrictions on the specific selection of the target detection model and the number classification model: The YOLOv8 (You Only Look Once version 8) model can be used to integrally implement the identification of the number area and the classification of the number; a combination of an identification model and a classification model can also be used. For example, the first target detection model can use a convolutional neural network, ViT (Vision Transformer), etc.; the classification model can use large models such as MobileNet, EfficientNet-Lite, or traditional machine learning models such as traditional vector machines and random forests.

[0065] S203: If the match is successful, obtain the jersey color of the human target with a successful match and match it with the target jersey color; if the match is successful, determine the human target with a successful match as the tracking target.

[0066] Since in a game, usually both competing sides have independent numbering rules, it is very likely that there will be two players with the same jersey number on the field. If tracking is based only on the jersey number, it is easy to have a situation of incorrect target recognition. Therefore, when the jersey number match in S202 is successful, in order to exclude misidentification caused by the above situation, the matching of the jersey color is introduced. The extraction of the jersey color can be directly implemented through the color picker API of the mobile terminal operating system. When performing color matching, due to reasons such as lighting or shooting angle, it is impossible to ensure that the second jersey color in the real-time video image is exactly the same as the first jersey color, and there may be a certain color difference. Therefore, the matching of the jersey color does not require the RGB three-channel values to be exactly the same, as long as the error does not exceed the preset threshold.

[0067] In one embodiment, the similarity between hue and saturation is measured by calculating the cosine of the angle between color vectors. The cosine of the angle is the ratio of the dot product of two color vectors to the product of their magnitudes, i.e., r(f,g)=(f·g) / (||f||·||g||). The closer the value of the cosine of the angle is to 1, the closer the hues and saturations of the two colors are. For example, if Color1=(216,8,24) and Color2=(240,16,16), then f·g = 216*240 + 8*16 + 24*16 = 52352, ||f||·||g||≈52,475.85, and the cosine of the angle is 0.999, indicating that their chromaticities are highly similar.

[0068] II. The tracking target is a crowd:

[0069] In the tracking shooting of sports, the crowd tracking mode is an implementation method for shooting the entire game. Crowd tracking takes the preset crowd in the real-time shooting image as the tracking target and judges the overall movement trend of the preset crowd. In the crowd tracking mode, the average value of the position coordinates of all targets in the crowd is regarded as the position of the crowd.

[0070] The crowd can be a set of all human target objects in the real-time shooting image, or a set of preset partial human target objects. For example:

[0071] (1) Detect the movement of the same team. For the judgment of the same team, the set of players with the same jersey color in the real-time shooting image is regarded as the same team, and then the average value of their position coordinates is calculated. The method for judging whether the jersey colors are the same has been described in detail above and will not be elaborated here.

[0072] (2) Detect the movement of the preset number of players with the fastest movement speed in the image. In ball games, there are often intense fast-break scenes. At this time, the movement speed of the players is very fast, and the preset number of players closest to the moving direction, that is, the players with the fastest movement speed, can be configured as three or five, and they are the focus of tracking. At this time, this crowd should be tracked in order to capture the most effective game images.

[0073] Specifically, first, the moving direction of the targets in the image is judged by continuous multi-frame. When the average value of the center points of all target frames in the image moves in the same direction continuously for several frames (depending on the frame rate of the shooting device, it can be set within 2 seconds. That is, if the frame rate of the shooting device is 60 frames per second, that is, 180 consecutive frames. In actual judgment, the real-time video can be frame-sampled before judgment) at a speed exceeding the threshold (the threshold depends on the frame rate and pixels of the shooting device and can be set to move 1000 pixels within 1 second), the current scene is recognized as a fast break, and the three or five people in the front part of all the people closest to the aforementioned direction are recognized as the tracking crowd, and then the average value of their position coordinates is calculated.

[0074] III. Tracking target is the ball:

[0075] Given the characteristics of ball games, the ball is the core target in such sports. The activities of players are all centered around the ball, and there is only one valid ball on the playing field at a given time. Therefore, the ball can be used as the tracking target.

[0076] When the ball is used as the tracking target, there may be occlusion. When the ball cannot be continuously recognized in the real-time captured image, it can be considered that the ball is continuously occluded and the ball is stationary at this time. For example, in the case of a free kick or a penalty kick in football, the ball is stationary and a large number of players surround the ball, causing occlusion. In view of this situation, preferably, several previous frames of the real-time captured image are traced back to find the position of the ball when it was last recognized as the current tracking position. Specifically, when the ball is not found in the real-time captured image, the recognition log of the recognition algorithm is traced forward to find the frame where the ball was last recognized, and this position is used as the current tracking target position.

[0077] For example, the timestamp information of the real-time captured image is 1736771678.5463305, and the ball is not recognized in the current frame. Tracing back to the log of the frame with a timestamp of 1736771678.2343305, there is a record of the last successful recognition of the ball:

[0078] "yolo":

[0079] {

[0080] "label": 0,

[0081] "confidence": 0.96,

[0082] "x": 552.0,

[0083] "y": 930.0,

[0084] "width": 50.0,

[0085] "height": 131.0

[0086] },

[0088] Among them, label is the label of the target box; confidence is the confidence level; x is the abscissa of the center point of the target box; y is the ordinate of the center point of the target box; width is the width of the target box; height is the height of the target box.

[0089] ​The predicted position of the ball has not changed. Therefore, the coordinates of the position where the ball was successfully recognized last time (552, 930) are used as the current tracking target position.

[0090] S2: When the position of the tracking target exceeds the first preset range, adjust the shooting angle of the pan-tilt head to track and shoot the tracking target.

[0091] The first preset range is adjustable and can be different according to different types of balls and different intensities of movement. If balanced composition is adopted, the target object should be located within the central one-third area of the screen. Therefore, the first preset range can be set in the center of the screen with an area of one-third of the screen size; if the golden ratio composition is adopted, the target object should be located at the golden ratio point on the left or right side of the screen, with an area ranging from one-fourth to one-third of the screen size. The present application does not limit the specific position and area of the first preset range.

[0092] The preset range can be expressed as [x, y] by the ratio of the distance from the side line to the center line of the screen to the length of the screen. Among them, a plane coordinate system is established with the center line of the screen as the y-axis. x is the ratio of the abscissa of the left side line of the first preset range to the total length of the screen, and y is the ratio of the abscissa of the right side line of the first preset range to the total length of the screen. For example, when the first preset range is set in the center of the screen with an area of one-third of the screen size, the first preset range can be expressed as [-1 / 6, 1 / 6].

[0093] Specifically, when the position of the tracking target is outside the left side of the first preset range, move the shooting angle of the pan-tilt head to the left until the position of the tracking target is back within the first preset range; when the position of the tracking target is outside the right side of the first preset range, move the shooting angle of the pan-tilt head to the right until the position of the tracking target is back within the first preset range. In a specific embodiment, when it is detected that the position of the tracking target is outside the first preset range, send a rotation command in the corresponding direction to the pan-tilt head to control the pan-tilt head to rotate a preset small angle, which can be set to 3° or 5° for example; at the next detection, if the position of the tracking target has returned within the first preset range, stop rotating; if the position of the tracking target is still outside the first preset range, continue to send the command to rotate the preset small angle.

[0094] S3: When the position of the fixed scoring area is within the second preset range and the position of the tracking target is within the third preset range, suspend the execution of S2 and lock the shooting angle of the pan-tilt head. The first preset range is included in the third preset range.

[0095] In this step, the position of the fixed scoring area is first identified. When the fixed scoring area in the real-time video frame is within the second preset range and the position of the tracking target does not exceed the third preset range, it is determined that the tracking target is moving within a small range around the fixed scoring area. At this time, even if the position of the tracking target exceeds the first preset range, S2 is not executed, but the shooting angle of the pan-tilt head is locked to fixedly shoot the activities of the tracking target around the fixed scoring area.

[0096] The second preset range is the position where the fixed scoring area is located in a conventional photographic composition. In a specific implementation, the second preset range can be the central two-thirds area of the real-time shooting frame, that is, [-1 / 3, 1 / 3]. When shooting a game on a relatively small venue, the ratio of the second preset range can be appropriately adjusted, such as adjusted to [-1 / 4, 1 / 4] or [-1 / 5, 1 / 5].

[0097] S3 is a special case step for the special scenario in step S2 under certain conditions, that is, the step executed when the tracking target has exceeded the first preset range but is still within the third preset range. It can be seen that the first preset range must be included in the third preset range. In a conventional game, the third preset range can be set to 1.5 times or 2 times the first preset range.

[0098] After executing the above three steps S1 - S3, when the specified target is tracked to stay around the fixed scoring area, the shooting angle can be locked to maintain the composition optimization and shooting stability within a certain range.

[0099] Preferably, in a possible implementation, the method may further include S4: when the position of the tracking target exceeds the third preset range, the locking of the shooting angle of the pan-tilt head is cancelled, and S2 is executed.

[0100] When the position of the tracking target exceeds the third preset range, it can be considered that the tracking target has left the range of the fixed scoring area. Therefore, the locking of the pan-tilt head is released, and S2 is executed again.

[0101] Figure 4 FIG. is an example diagram of an automatic tracking shooting method for the movement of a fixed scoring area according to an embodiment of the present application. This example is provided for easy understanding and should not be regarded as the only implementation.

[0102] Taking an automatic tracking shooting of a basketball game as an example, in the real-time shooting frame, the first preset range is configured as [-1 / 6, 1 / 6], the second preset range is configured as [-1 / 4, 1 / 4], and the third preset range is configured as [-1 / 3, 1 / 3].

[0103] Under normal circumstances, when the tracking target is outside the first preset range, such as in areas A, B, or C, according to the logic of step S2, the pan-tilt head should be controlled to rotate to the left until the tracking target is again within area D.

[0104] However, when the basket is within the second preset range, such as in areas C or D, even if the tracking target is outside the first preset range but within the third preset range, such as in area B, stop executing S2 and lock the pan-tilt head angle to capture a fixed image.

[0105] In a possible implementation, it is possible to determine whether to lock the pan-tilt head angle by judging the number of human targets present within the fixed scoring area.

[0106] Figure 5 Shows a flowchart of another automatic tracking shooting method for the movement of the fixed scoring area according to an embodiment of the present application. As Figure 5 shown:

[0107] S31: When the position of the fixed scoring area is within the second preset range and the number of human targets within the second preset range is not less than the preset value, suspend the execution of S2 and lock the shooting angle of the pan-tilt head.

[0108] S41: When the number of human targets within the second preset range is less than the preset value, cancel the locking of the pan-tilt head angle and execute step S2.

[0109] Use a target recognition algorithm to identify human targets. The specific selection of the target recognition algorithm has been mentioned above and will not be elaborated here. Specifically, judge whether the human target is within the second preset range based on the abscissa of the midpoint of the human target recognition frame obtained by the target recognition algorithm.

[0110] The setting of the preset value is related to the type of competition: In a possible implementation, after browsing and counting a large number of competition videos, the preset value can be set to 60% - 80% of the total number of active players on the field. For example, in a basketball game, if the total number of active players is 10, the preset value can be set to 6 - 8; in a football game, if the total number of active players is 20, the preset value can be set to 12 - 14.

[0111] Specifically, when there are fixed scoring areas and more than the preset value of players within the second preset range, lock the pan-tilt head angle to fixedly capture the activities of the players around the fixed scoring area.

[0112] Figure 6 Is a block diagram of an automatic tracking shooting device 400 according to an embodiment of the present application. As Figure 6As shown, the automatic tracking shooting device 400 includes a shooting module 401, an analysis module 402, and a rotation module 403. The automatic tracking shooting device 400 is used to implement the foregoing automatic shooting tracking method.

[0113] Optionally, the automatic tracking shooting device 400 can be an independent device, or a component included in an independent device, or a combination of multiple different independent devices. In a possible implementation, the shooting module 401 is implemented as an independent intelligent terminal or camera, the analysis module 402 is implemented as another independent intelligent terminal or intelligent hardware, and the rotation module 403 is implemented as a pan-tilt or rotatable bracket. In another possible implementation, the shooting module 401 is implemented as a camera module in an intelligent terminal, the analysis module 402 is implemented as a computing module in the same intelligent terminal, and the rotation module 403 is implemented as an intelligent pan-tilt or rotatable bracket. In yet another possible implementation, the shooting module 401 is implemented as a camera module in an integrated intelligent imaging device, the analysis module 402 is implemented as a computing module in the same integrated intelligent imaging device, and the rotation module 403 is implemented as a motion mechanism in the same integrated intelligent imaging device.

[0114] Among them, the shooting module 401 is physically connected to the rotation module 403. The physical connection can be a fixed connection or a detachable connection, as long as it can ensure that the rotation module 403 can directly or indirectly affect the movement of the shooting module 401 physically. The shooting module 401 is adapted to continuously acquire real-time shooting images and send the real-time shooting images to the analysis module 402. Optionally, the shooting module 401 may not have an active information sending function, but the analysis module 402 actively obtains the real-time shooting images from the shooting module 401. The analysis module 402 is adapted to execute the method in the embodiment of the present application based on the real-time shooting images Figure 1 or Figure 2 to perform real-time calculation and judgment on the tracking center position, and send a rotation instruction to the rotation module 403 according to the judgment condition. The rotation module 403 is adapted to rotate horizontally, that is, rotate around the vertical axis (z-axis). The rotation module 403 is adapted to change the angle of the shooting module 401 according to the rotation instruction.

[0115] Figure 7 shows a schematic structural diagram of a terminal device or server suitable for implementing the embodiments of the present application.

[0116] As Figure 7As shown, the terminal device or server includes a central processing unit (CPU) 501, which can perform various appropriate actions and processes according to a program stored in a read-only memory (ROM) 502 or a program loaded from a storage section 508 into a random access memory (RAM) 503. In the RAM 503, various programs and data required for the operation of the terminal device or server are also stored. The CPU 501, ROM 502, and RAM 503 are connected to each other via a bus 504. An input / output (I / O) interface 505 is also connected to the bus 504.

[0117] The following components are connected to the I / O interface 505: an input section 506 including a keyboard, a mouse, etc.; an output section 507 including a cathode ray tube (CRT), a liquid crystal display (LCD), etc. and a speaker, etc.; a storage section 508 including a hard disk, etc.; and a communication section 509 including a network interface card such as a LAN card, a modem, etc. The communication section 509 performs communication processing via a network such as the Internet. A drive 510 is also connected to the I / O interface 505 as needed. A removable medium 511, such as a magnetic disk, an optical disk, a magneto-optical disk, a semiconductor memory, etc., is mounted on the drive 510 as needed so that a computer program read from it can be installed into the storage section 508 as needed.

[0118] Specifically, according to an embodiment of the present application, the above method flow steps can be implemented as a computer software program. For example, an embodiment of the present application includes a computer program product, which includes a computer program carried on a machine-readable medium, and the computer program includes program codes for performing the method shown in the flowchart. In such an embodiment, the computer program can be downloaded and installed from the network via the communication section 509, and / or installed from the removable medium 511. When the computer program is executed by a central processing unit (CPU) 501, the above functions defined in the system of the present application are executed.

[0119] It should be noted that the computer-readable medium shown in this application can be a computer-readable signal medium, a computer-readable storage medium, or any combination of the two. A computer-readable storage medium can be, for example, but not limited to, an electrical, magnetic, optical, electromagnetic, infrared, or semiconductor system, apparatus, or device, or any combination of the above. More specific examples of a computer-readable storage medium can include, but are not limited to: an electrical connection with one or more wires, a portable computer disk, a hard disk, a random access memory (RAM), a read-only memory (ROM), an erasable programmable read-only memory (EPROM or flash memory), an optical fiber, a portable compact disk read-only memory (CD-ROM), an optical storage device, a magnetic storage device, or any suitable combination of the above. In this application, a computer-readable storage medium can be any tangible medium that contains or stores a program that can be used by or in conjunction with an instruction execution system, apparatus, or device. And in this application, a computer-readable signal medium can include a data signal propagated in a baseband or as part of a carrier wave, which carries computer-readable program code. Such a propagated data signal can take various forms, including but not limited to electromagnetic signals, optical signals, or any suitable combination of the above. A computer-readable signal medium can also be any computer-readable medium other than a computer-readable storage medium, which can send, propagate, or transmit a program for use by or in conjunction with an instruction execution system, apparatus, or device. The program code contained on a computer-readable medium can be transmitted using any appropriate medium, including but not limited to: wireless, wire, optical cable, RF, etc., or any suitable combination of the above.

[0120] The flowcharts and block diagrams in the accompanying drawings illustrate the possible architectures, functions, and operations of systems, methods, and computer program products according to various embodiments of this application. In this regard, each block in a flowchart or block diagram can represent a module, a program segment, or a part of code, and the foregoing module, program segment, or part of code contains one or more executable instructions for implementing a specified logical function. It should also be noted that in some alternative implementations, the functions marked in the blocks may occur in a different order than marked in the accompanying drawings. For example, two consecutive blocks shown may actually be executed substantially in parallel, and they may sometimes be executed in the reverse order, depending on the functions involved. It should also be noted that each block in the block diagram and / or flowchart, and the combination of blocks in the block diagram and / or flowchart, can be implemented by a dedicated hardware-based system for performing the specified functions or operations, or can be implemented by a combination of dedicated hardware and computer instructions.

[0121] The units or modules involved in the embodiments described in this application can be implemented in software or in hardware. The described units or modules can also be provided in a processor. Among them, the names of these units or modules do not, in some cases, constitute a limitation on the units or modules themselves.

[0122] As another aspect, this application also provides a computer-readable storage medium, which can be included in the electronic device described in the foregoing embodiments; or can exist separately without being assembled into the electronic device. The foregoing computer-readable storage medium stores one or more programs, and when the foregoing programs are executed by one or more processors, they implement the methods described in this application.

[0123] The above description is only a preferred embodiment of this application and an explanation of the technical principles applied. Those skilled in the art should understand that the scope of the application involved in this application is not limited to the technical solutions formed by the specific combination of the above technical features, but should also cover other technical solutions formed by any combination of the above technical features or their equivalent features without departing from the foregoing application concept. For example, the technical solutions formed by mutually replacing the above features with the technical features (but not limited to) having similar functions described in this application.

Claims

1. An automatic tracking shooting method for the movement of a fixed scoring area, characterized in that, Including: S1: Identify the position of the tracking target and the position of the fixed scoring area in the real-time captured image. S2: When the position of the tracking target exceeds the first preset range, adjust the shooting angle of the pan-tilt head to track and shoot the tracking target. S3: When the position of the fixed scoring area is within the second preset range and the position of the tracking target is within the third preset range, suspend the execution of S2 and lock the shooting angle of the pan-tilt head. The first preset range is included in the third preset range.

2. The method according to claim 1, wherein The tracking target is at least one of a player, a crowd, or a ball.

3. The method according to claim 1, wherein Also including: S4: When the position of the tracking target exceeds the third preset range, cancel the locking of the shooting angle of the pan-tilt head and execute S2.

4. The method according to claim 1, wherein When the position of the tracking target exceeds the first preset range, adjusting the shooting angle of the pan-tilt head includes: When the position of the tracking target is outside the left side of the first preset range, shift the shooting angle of the pan-tilt head to the left until the position of the tracking target is again within the first preset range. When the position of the tracking target is outside the right side of the first preset range, shift the shooting angle of the pan-tilt head to the right until the position of the tracking target is again within the first preset range.

5. The method according to claim 2, wherein When the tracking target is a player, identifying the position of the tracking target in the real-time captured image includes: Pre-acquire the jersey features of the tracking target, where the jersey features include the target jersey number and the target jersey color. Acquire all human targets in the real-time captured image, crop the jersey number area of each human target and send it to the number classification model, obtain the jersey number of each human target, and match it with the target jersey number. If the match is successful, obtain the jersey color of the human target with a successful match and match it with the target jersey color. If the match is successful, determine the human target with a successful match as the tracking target.

6. The method according to claim 2, wherein When the tracking target is a crowd, use the average value of the position coordinates of all targets in the crowd as the position of the tracking target.

7. The method according to claim 2, characterized in that When the tracking target is a ball, identifying the position of the tracking target in the real-time captured image includes: When the tracking target cannot be identified in the real-time captured image, trace back to the first position of the tracking target when it was last identified in the preset number of frames before the real-time captured image, and use the first position as the position of the tracking target.

8. An automatic tracking shooting device, characterized in that, It includes a shooting module, an analysis module, and a rotation module. The shooting module is physically connected to the rotation module. The rotation module is suitable for horizontal rotation. The shooting module is suitable for continuously acquiring real-time captured images and sending the real-time captured images to the analysis module. The analysis module is suitable for executing the method according to any one of claims 1-7 and sending a rotation instruction to the rotation module. The rotation module is suitable for changing the angle of the shooting module according to the rotation instruction.

9. An electronic device, comprising a memory and a processor, wherein a computer program is stored on the memory, characterized in that, When the processor executes the computer program, it implements the method according to any one of claims 1-7.

10. A computer-readable storage medium having a computer program stored thereon, characterized in that, When the computer program is executed by the processor, it implements the method according to any one of claims 1-7.

Images